Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2130 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.9327. Min Act: -0.1700
Data Index: 2681900 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.7451. Min Act: -0.1700
Data Index: 6028167 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.7451. Min Act: -0.1700
Data Index: 2948276 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.7451. Min Act: -0.1700
Data Index: 2112060 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.6825. Min Act: -0.1700
Data Index: 5412086 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.6356. Min Act: -0.1700
Data Index: 4334952 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.5416. Min Act: -0.1700
Data Index: 1539973 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.5730. Min Act: -0.1700
Data Index: 2618139 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.5730. Min Act: -0.1700
Data Index: 4813904 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.5416. Min Act: -0.1700
Data Index: 3208305 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.5416. Min Act: -0.1700
Data Index: 7143170 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.5103. Min Act: -0.1700
Data Index: 8130798 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.5260. Min Act: -0.1700
Data Index: 3537410 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.5103. Min Act: -0.1700
Data Index: 1799545 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.5260. Min Act: -0.1700
Data Index: 4318607 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.5103. Min Act: -0.1700
Data Index: 5959767 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.4790. Min Act: -0.1700
Data Index: 2192563 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.4947. Min Act: -0.1700
Data Index: 2627380 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.4790. Min Act: -0.1700
Data Index: 6179303 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9327. Min Range: -3.9327
Max Act: 3.4947. Min Act: -0.1700
Data Index: 7788087 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19